© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99404
    Prev
    Next
    INDEX
    Explanations

    percentage values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectivos
    -1.57
     bustling
    -1.55
     treinamento
    -1.50
     constitución
    -1.50
     recibir
    -1.47
    驺
    -1.46
     lâmpada
    -1.45
    ЧИ
    -1.44
     svoj
    -1.43
     vč
    -1.43
    POSITIVE LOGITS
     (%)
    1.87
    Andere
    1.66
    ↵
    1.66
     iliy
    1.59
     chance
    1.59
     of
    1.49
    Zubereitung
    1.48
     percent
    1.48
    Danke
    1.45
     مردم
    1.44
    Activations Density 0.098%

    No Known Activations